WongKinYiu / yolor

implementation of paper - You Only Learn One Representation: Unified Network for Multiple Tasks (https://arxiv.org/abs/2105.04206)
GNU General Public License v3.0
1.98k stars 524 forks source link

What hardware used for FPS measure? Can't get even closer. #178

Closed dtyugin closed 2 years ago

dtyugin commented 2 years ago

I can get only ~16 FPS (60 ms inference time) on 1280 image while using weights for yolor p6, which is too far from 76 FPS. I'm using pytorch 1.8 and GTX 1080Ti with cuda 11.0. Could you please tell which hardware was used in benchmarking?

dtyugin commented 2 years ago

Found under the curve, V100.